{"id":58424,"date":"2020-08-07T19:17:11","date_gmt":"2020-08-07T10:17:11","guid":{"rendered":"https:\/\/smilegate.ai\/?p=58424"},"modified":"2020-08-16T22:35:02","modified_gmt":"2020-08-16T13:35:02","slug":"google-mixit-ai","status":"publish","type":"post","link":"https:\/\/smilegate.ai\/en\/2020\/08\/07\/google-mixit-ai\/","title":{"rendered":"Google MixIT AI-Separation of unsupervised learning sound sources"},"content":{"rendered":"

MixIT AI, unveiled by Google, is a technology that obtains a separate sound source from single channel audio in which multiple sound sources are mixed. It can be viewed as a blind source separation task, and unlike existing technologies, it is characterized by excellent performance with unsupervised(!).<\/p>\n\n\n\n

The recent trend is clear. Unsupervised, self-supervised, semi-supervised, the names are slightly different, but in the end what you want is to catch up with performance by using unlabeled data on a large scale, rather than having a medium-sized labeled data. And adding more data there or achieving SOTA with very little labeling data.<\/p>\n\n\n\n

<\/div>\n\n\n
<\/a>
\"\"<\/div><\/div>
Google's MixIT AI isolates speakers in audio recordings<\/div>
In a new paper, researchers at Google describe an AI system that isolates speakers' voices in audio recordings using an unsupervised approach.<\/div><\/div><\/div>
<\/span><\/div>","protected":false},"excerpt":{"rendered":"

Google\uc774 \uacf5\uac1c\ud55c MixIT AI\ub294 \ubcf5\uc218\uac1c \uc74c\uc6d0\uc774 \ubbf9\uc2f1\ub41c \uc2f1\uae00 \ucc44\ub110 \uc624\ub514\uc624\ub85c\ubd80\ud130 \ubd84\ub9ac\ub41c \uc74c\uc6d0\uc744 \uc5bb\ub294 \uae30\uc220\uc785\ub2c8\ub2e4. Blind source separation task\ub77c\uace0 \ubcfc \uc218 \uc788\ub294\ub370, \uae30\uc874 \uae30\uc220\ub4e4\uacfc\ub294 \ub2ec\ub9ac unsupervised(!)\ub85c \uc6b0\uc218\ud55c \uc131\ub2a5\uc744 \ub0b8\ub2e4\ub294 \ud2b9\uc9d5\uc774 \uc788\uc2b5\ub2c8\ub2e4. \ucd5c\uadfc\uc758 \ud2b8\ub80c\ub4dc\ub294 \ud655\uc2e4\ud558\ub124\uc694. Unsupervised, self-supervised, semi-supervised, \uc774\ub984\uc740 \uc870\uae08\uc529 \ub2e4\ub974\uc9c0\ub9cc \uacb0\uad6d \uc6d0\ud558\ub294 \uac83\uc740 \ub77c\ubca8\ub9c1\ub41c \ub370\uc774\ud130\ub97c \uc911\uaddc\ubaa8 \ud655\ubcf4\ud558\ub294 \ub300\uc2e0, \ub77c\ubca8\ub9c1\ub418\uc9c0 \uc54a\uc740 \ub370\uc774\ud130\ub97c \ub300\uaddc\ubaa8\ub85c \uc0ac\uc6a9\ud558\uc5ec \uc131\ub2a5\uc744 \ub530\ub77c\uc7a1\ub294 \uac83.…<\/p>\n

<\/span><\/div>","protected":false},"author":1,"featured_media":58577,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[17],"tags":[228,229,230,231],"_links":{"self":[{"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/posts\/58424"}],"collection":[{"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/comments?post=58424"}],"version-history":[{"count":0,"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/posts\/58424\/revisions"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/media\/58577"}],"wp:attachment":[{"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/media?parent=58424"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/categories?post=58424"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/smilegate.ai\/en\/wp-json\/wp\/v2\/tags?post=58424"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}